collaborators

32 papers

cs.LG2026

Invariant Reasoning Directions in Latent Trajectories of Language Models

Arun Vignesh Malarkkan, Manan Roy Choudhury, Utkarsh Byahut +3

Latent reasoning models perform multi-step inference directly in hidden-state space, yet the structure of these latent reasoning trajectories remains poorly understood. We show tha…

cs.LG2026

PageLLM: A Multi-Grained Reward Framework for Whole-Page Optimization with Large Language Models

Xinyuan Wang, Liang Wu, Dongjie Wang +1

Whole-page optimization (WPO) decides how search and recommendation results are surfaced to users, and large language models (LLMs) open a new route to it by treating page generati…

cs.AI2026

Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations

Nanxu Gong, Zixin Chen, Haotian Li +5

Improving the Theory of Mind (ToM) capability of Large Language Models (LLMs) is crucial for effective social interactions between these AI models and humans. However, the existing…

cs.AI2026

FinRule-Bench: A Benchmark for Joint Reasoning over Financial Tables and Principles

Arun Vignesh Malarkkan, Manan Roy Choudhury, Guangwei Zhang +4

Large language models (LLMs) are increasingly applied to financial analysis, yet their ability to audit structured financial statements under explicit accounting principles remains…

cs.AI2026

To Think or Not To Think, That is The Question for Large Reasoning Models in Theory of Mind Tasks

Nanxu Gong, Haotian Li, Sixun Dong +3

Theory of Mind (ToM) assesses whether models can infer hidden mental states such as beliefs, desires, and intentions, which is essential for natural social interaction. Although re…

cs.CV2026

MMTok: Multimodal Coverage Maximization for Efficient Inference of VLMs

Sixun Dong, Juhua Hu, Mian Zhang +3

Vision-Language Models (VLMs) demonstrate impressive performance in understanding visual content with language instruction by converting visual inputs to vision tokens. However, re…